{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SSOLXEGGTIIREP75RP3DHGDITX","short_pith_number":"pith:SSOLXEGG","schema_version":"1.0","canonical_sha256":"949cbb90c69a11123ffd8bf63398689dfd12d67cd6f0f3153a0193e20fbcdaad","source":{"kind":"arxiv","id":"2606.22339","version":1},"attestation_state":"computed","paper":{"title":"T-IMPACT: A Severity-Aware Benchmark for Contextual Image-Text Manipulation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaditya Yadav, Gagandeep Singh, Priyanka Singh","submitted_at":"2026-06-21T05:07:20Z","abstract_excerpt":"Recent advances in vision-language models and generative editing systems have made it increasingly easy to produce persuasive multimodal misinformation by altering images, text, or both jointly. However, existing datasets focus mainly on authenticity, out-of-context mismatch, or manipulation type, and rarely capture how strongly an edit changes the likely interpretation of a post. We introduce T-IMPACT, a first-release severity-aware benchmark for manipulated news-style image-text pairs. T-IMPACT contains 98,786 examples spanning pristine, image-only, text-only, and joint manipulations, with a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.22339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T05:07:20Z","cross_cats_sorted":[],"title_canon_sha256":"ec95caee0c948f7924a11d95f452e31ad4a7ac02a1965a9060a66a340c9ca88f","abstract_canon_sha256":"f14362b9faa69390d1cfa9968f5be948e31d1ce078e7113b288271d2c61831c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:35.210555Z","signature_b64":"o7kUbIhFmixb3/vzPKFsFoPixzlT29ipv1MnxrPNTHLKiixk0WMiTHSb2yjnnURs9d/wU2T0IRJhRFi4p6hFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"949cbb90c69a11123ffd8bf63398689dfd12d67cd6f0f3153a0193e20fbcdaad","last_reissued_at":"2026-06-23T02:13:35.210185Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:35.210185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T-IMPACT: A Severity-Aware Benchmark for Contextual Image-Text Manipulation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaditya Yadav, Gagandeep Singh, Priyanka Singh","submitted_at":"2026-06-21T05:07:20Z","abstract_excerpt":"Recent advances in vision-language models and generative editing systems have made it increasingly easy to produce persuasive multimodal misinformation by altering images, text, or both jointly. However, existing datasets focus mainly on authenticity, out-of-context mismatch, or manipulation type, and rarely capture how strongly an edit changes the likely interpretation of a post. We introduce T-IMPACT, a first-release severity-aware benchmark for manipulated news-style image-text pairs. T-IMPACT contains 98,786 examples spanning pristine, image-only, text-only, and joint manipulations, with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22339","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.22339/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.22339","created_at":"2026-06-23T02:13:35.210250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22339v1","created_at":"2026-06-23T02:13:35.210250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22339","created_at":"2026-06-23T02:13:35.210250+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSOLXEGGTIIR","created_at":"2026-06-23T02:13:35.210250+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSOLXEGGTIIREP75","created_at":"2026-06-23T02:13:35.210250+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSOLXEGG","created_at":"2026-06-23T02:13:35.210250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX","json":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX.json","graph_json":"https://pith.science/api/pith-number/SSOLXEGGTIIREP75RP3DHGDITX/graph.json","events_json":"https://pith.science/api/pith-number/SSOLXEGGTIIREP75RP3DHGDITX/events.json","paper":"https://pith.science/paper/SSOLXEGG"},"agent_actions":{"view_html":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX","download_json":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX.json","view_paper":"https://pith.science/paper/SSOLXEGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22339&json=true","fetch_graph":"https://pith.science/api/pith-number/SSOLXEGGTIIREP75RP3DHGDITX/graph.json","fetch_events":"https://pith.science/api/pith-number/SSOLXEGGTIIREP75RP3DHGDITX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX/action/storage_attestation","attest_author":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX/action/author_attestation","sign_citation":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX/action/citation_signature","submit_replication":"https://pith.science/pith/SSOLXEGGTIIREP75RP3DHGDITX/action/replication_record"}},"created_at":"2026-06-23T02:13:35.210250+00:00","updated_at":"2026-06-23T02:13:35.210250+00:00"}